Radeon Power Management Still An Incomplete Mess

[89c51]

People that just want to watch youtube videos probably aren't running Linux. The percentage of Linux users that want fast OpenCL is actually pretty large. Most large scale Linux users are not consumers.

I was (and probably Adarion) referring to the average joe linux user and not the corporate/large scale type.

And i don't think the corporate/large scale care about open source OpenCL. They'll probably just use the blob and get their job done. And even the average joe will install a blob because he want's VA, Games, PM etc.

[tstrunk]

And i don't think the corporate/large scale care about open source OpenCL. They'll probably just use the blob and get their job done. And even the average joe will install a blob because he want's VA, Games, PM etc.

They don't care about open source, true, but they care about hassle-free. Implementing OpenCL using Catalyst on a HPC architecture is a pain and you need to break some best practices to do it, like install a X-Server and make it permissive. I can only assume the open source driver would allow for a better solution.
Still of course, Performance is king. If an open source driver wouldn't attain performance parity with the closed source solution, it wouldn't be used also on HPC no matter the security holes.

On the other hand for office terminals the open source drivers are working great and hassle free.

[libv]

"Just release the code already, and arrange for anyone who tries to block it to find a new position where being an idiot is acceptable."

Thanks Dave!

That's nice. Now think back 5 years and wonder why ATI was more than keen to work with Dave than with us. We at SuSE were aiming too high (as in, reducing the relevance of fglrx) and we were asking too many nasty questions for ATIs liking (many of those ATI were simply incapable or unwilling to answer). We were getting blocked on so many sides by the end, not only by ATI, but also by supposed open source people. So I am still waiting to see that logic applied comprehensively, which in this case, includes the person quoted.

So stop complaining, Dave. You played a key role in reducing the set of requirements AMD had for ATI. Now go and sit on the blisters. (and before you try to complain; why don't you get back to me when more documentation than just the shader isa, released by the AMD gpgpu people, and not by the mess-formerly-known-as ATI, is being released again - as we at SuSE required)

[tstrunk]

That's nice. Now think back 5 years and wonder why ATI was more than keen to work with Dave than with us. We at SuSE were aiming too high (as in, reducing the relevance of fglrx) and we were asking too many nasty questions for ATIs liking (many of those ATI were simply incapable or unwilling to answer). We were getting blocked on so many sides by the end, not only by ATI, but also by supposed open source people. So I am still waiting to see that logic applied comprehensively, which in this case, includes the person quoted.

So stop complaining, Dave. You played a key role in reducing the set of requirements AMD had for ATI. Now go and sit on the blisters. (and before you try to complain; why don't you get back to me when more documentation than just the shader isa, released by the AMD gpgpu people, and not by the mess-formerly-known-as ATI, is being released again - as we at SuSE required)

Just assigning blame won't help anyone. At the moment the whole situation here is escalating.
The reason for that is simple:

a) People don't trust bridgeman anymore
b) the uninformed users (me included) go on the nerves of the informed people
c) countless useless flames
d) the current situation between you two.

Might I therefore suggest the following strategy for de-escalation: Michael could setup a forum, where only X developers and people selected by them (bridgeman for example) have access and everybody else only gets read access.
I believe everyone of you has the same goal: To make the open driver better. The fragmented discussion in the current style will only make matters worse over time. In the single forum you can record your demands to AMD/ATI, bridgeman can answer and you can respond without people crying foul in between.

[89c51]

a) People don't trust bridgeman anymore

I don't think bridgman ever did something wrong. And for sure he never promised that they will release code (PM and UVD) for sure. He said they were investigating it. This and peoples hopes or desires are two different things.

[tstrunk]

I don't think bridgman ever did something wrong. And for sure he never promised that they will release code (PM and UVD) for sure. He said they were investigating it. This and peoples hopes or desires are two different things.

I don't think so either. I also never said he promised something, I just said the normal users here don't trust him so much anymore. I feel for him, because I had to do a similar job once. I don't think it would be a good thing, if he quits. But read the thread until now and you will see what I mean. He gets flamed all the time and due to all the noise, you cannot really make out, when he really 'represented the company' or told the actual truth.

A separate forum without most of the people here would avoid all that flaming and still keep the masses entertained, because they would be informed.

[brent]

I can only echo David Arlie's comments. I investigated the PM situation, read a lot of code and datasheets, with the goal of improving it on APUs. There's very, very little substantial information available (in code, extracted from mailing list posts or real documentation/datasheets) and it's hidden well. A lot of guessing, reverse engineering and trial and error is required, and debugging this stuff is *hard*. In other words, without documentation or a (quality) code drop, PM will never be fixed.

My problem with bridgman is that he has a tendency to justify the crazy decisions made by AMD and to downplay how bad the state of the drivers really is. And teasing people doesn't bode well either ("we have some PM code and we *might* release it").

[enrico.tagliavini]

I totally agree with Airlie. I have been an AMD customer for many years. I tried the open source radeon driver many times on different hardware (from r200 to r700) and the fglrx expirience was simply better (with all the problem it had!). AMD just have to wake up and begin a serious open source strategy. If AMD want to rely on the community it should be more open to collaboration. But the best solution is the intel one: set up a big open source center and start developing the driver all around. Not just the begin and from there to the community. This doesn't work if you don't collaborate more. And I want to be clear: nothing bad from the radeon AMD team. They are just amazing, always open to discuss and help. This problem is far upper then them, they just don't care about linux IMHO.

[necro-lover]

My problem with bridgman is that he has a tendency to justify the crazy decisions made by AMD and to downplay how bad the state of the drivers really is. And teasing people doesn't bode well either ("we have some PM code and we *might* release it").

What is your problem? This exactly this is his job!

His job is to justify the Corporatism conspiracy against FOSS.

The Corporatism logic from ground up: The plan was always give away a small salami slice to the Social-Movement(FOSS) and the 99% of the big salami goes into the corrupt and anti-social Closed-Source bucket.

And the winner is: Commercial company’s like Microsoft/Apple and the loser is: FOSS

They do this game until the people get the point and stand up and fight for there rights in this case fight for FOSS. If they don't do this AMD will not chance there behaviour because they are very successful with there behaviour.

The FOSS people can only escape this trap if they buy hardware like: ARM or Loongson hardware. (its about market-share in the market section and compatibility to windows/macos)

[89c51]

But read the thread until now and you will see what I mean. He gets flamed all the time and due to all the noise, you cannot really make out, when he really 'represented the company' or told the actual truth.

Apart from a few morons i don't thinks there is a problem with flaming. Most of the people understand that HW companies are just that. Organizations making money. Some are more "helpful" than others when it comes to FOSS but that doesn't mean that everyone in the management necessarily understand free and open or want to be free and open.